[IAEP] SOMs and Constructionism

[Gary C Martin]

Hi Teemu,

I was just having a run though and uploading SOM maps for some of the  
papers posted on both laptop.org and sugarlabs.org pages*** While I  
was at it I decide to add in your paper and generate a new SOM image  
for it. I've been tweaking and fine tuning my code and word metric  
extraction filters since I started making SOMs for the mail lists, so  
this map is looking a lot cleaner/clearer than the one I sent you way  
back in May:

	http://sugarlabs.org/go/Community/SOM#SOM_Related_Research_Papers

Feel free to edit the page if needed (incase I didn't cite correctly  
or something, I'm not in academia so don't know all the etiquette).  
Would be happy to cite some additional SOM related papers here (and  
generate SOMs for them) if you can suggest a few particularly salient  
ones.

***I added links to the various wiki pages with SOMs + papers on my  
sugarlabs user page http://sugarlabs.org/go/User:Garycmartin – if  
you're looking for them – just to keep track.

Regards,
--Gary

P.S. I'm a little further on with generating SOMs based on separate  
text documents (the more common usage so I've read). The plan still  
being to point it at the wiki (or some sub-section initially), and  
have the SOM generate a content map with click-able links to the  
pages. The big problem I find with active wikis is how quickly they  
become a complex ball of tangled string - I'm hoping that generating a  
reasonably upto-date, top level, content page map is going to help. If  
that seems to work, I'll be tempted to do something similar for the  
Sugar python code so I can generate actual source code maps showing  
how the classes/modules/methods are related in the implementation.

On 20 May 2008, at 03:02, Teemu Leinonen wrote:

> Hi Gary,
>
> Thank you Gary. Really nice. I think your SOM visualization are the  
> most human-readable I have seen. What software you are using to  
> generate these? Is it open source?
>
> Would it be anyhow possible to make the map interactive so that  
> clicking the concepts could bring some  relevant texts snippets /  
> quotations from the textual data?
>
> I also have the idea that one should be able to make a SOMs out of a  
> large quantity of scientific articles about some discipline and then  
> have a SOM out of "learning discussions" (e.g. a news group)  
> overlapping (like a layer) the "expert map" to compare them.
>
> For instance I would love to compare the SOM:
>
> http://garycmartin.com/som/2008-May-its-an-education-project-list-som.jpg
>
> ...to SOM made out of articles in educational technology journals in  
> last 10 years. I am pretty sure these two maps wouldn't match very  
> well, thought they both are claiming to be "education projects" :-)
>
> 	- Teemu
>
> Gary C Martin kirjoitti 19.5.2008 kello 14:46:
>
>> Hi Teemu,
>>
>> Thanks for pointing out your paper. I ran the text through the SOM  
>> code – though it's perhaps a little on the short side for my  
>> current analysis method – here's the link to the map generated:
>>
>> 	http://garycmartin.com/som/teemu_leinonen_som_learning_som.jpg
>>
>> --Gary
>>
>> On 19 May 2008, at 02:39, Teemu Leinonen wrote:
>>
>>> Hi all,
>>>
>>> Related to Gary's SOM analyzes / visualizations: With colleagues  
>>> we have published the following article:
>>>
>>> Honkela T., Leinonen T., Lonka K., Raike A. (2000): Self- 
>>> Organizing Maps and Constructive Learning. Proceedings of  
>>> ICEUT'2000, International Conference on Educational Uses of  
>>> Communication and Information Technologies, Beijing, China. August  
>>> 21-25, 2000, pp. 339-343.
>>> PDF: http://www2.uiah.fi/~tleinone/teemu_leinonen_som_learning.pdf
>>>
>>> If not more, in the end of the short paper there are some good  
>>> references to learning theories, computer supported collaborative  
>>> learning (CSCL) and Self-Organizing Maps.
>>>
>>> Best regards,
>>>
>>> 	- Teemu
>>>
>>> its.an.education.project-request at tema.lo-res.org kirjoitti  
>>> 18.5.2008 kello 14:36:
>>>
>>>> Subject: Re: [Its.an.education.project] Fwd:  
>>>> Its.an.education.project
>>>> 	curiosity
>>>> To: Gary C Martin <gary at garycmartin.com>
>>>> Cc: its.an.education.project at tema.lo-res.org
>>>> Message-ID: <4830231B.3020507 at student.tuwien.ac.at>
>>>> Content-Type: text/plain; charset=windows-1252; format=flowed
>>>>
>>>> Gary,
>>>>
>>>> excellent work, I love the map!
>>>>
>>>> Maybe this is something that we could add to Walter's SugarLabs  
>>>> digest
>>>> on a monthly/weekly basis?
>>>>
>>>> Cheers,
>>>> Christoph
>>>>
>>>> Gary C Martin schrieb:
>>>>> Hi List,
>>>>>
>>>>> I sent this to Marco, off-list, as a curiosity (I'm not currently
>>>>> subscribed to its.an.education.project so please cc me if needed).
>>>>> It's basically a self organising map (SOM) visualisation of the  
>>>>> new
>>>>> list activity up to a day or two ago (more description of the
>>>>> visualisation technique in my email below). Here's a link to the  
>>>>> image:
>>>>>
>>>>>   http://garycmartin.com/som/2008-May-its-an-education-project-list-som.jpg
>>>>>
>>>>>
>>>>> I was trying to get an idea for the topics being covered here  
>>>>> without
>>>>> burning my time by reading all of the archive, but if folks find  
>>>>> it of
>>>>> some use I could automate the process. Perhaps monthly/weekly list
>>>>> views, wiki content, etc?
>>>>>
>>>>> --Gary
>>>>>
>>>>> Begin forwarded message:
>>>>>
>>>>>> This is very nice! I'd actually post it on the list, you don't  
>>>>>> need to
>>>>>> be subscribed to do so...
>>>>>>
>>>>>> Cheers,
>>>>>> Marco
>>>>>>
>>>>>> On Sat, May 17, 2008 at 5:42 AM, Gary C Martin <gary at garycmartin.com 
>>>>>> >
>>>>>> wrote:
>>>>>>> Hi Marco,
>>>>>>>
>>>>>>> Just a random aside, didn't want to post formally as this is  
>>>>>>> just a
>>>>>>> rough,
>>>>>>> but though you might find it vaguely interesting/curious.
>>>>>>>
>>>>>>> I recently noticed the its.an.education.project, but I'm  
>>>>>>> reticent to
>>>>>>> join
>>>>>>> yet another list that potentially another set of distracting  
>>>>>>> rants or a
>>>>>>> talking shop ? be they good or bad, my opinion reading  
>>>>>>> bandwidth is
>>>>>>> pretty
>>>>>>> saturated now with the existing lists... Anyway, I've been  
>>>>>>> working
>>>>>>> on a Self
>>>>>>> Organising Map (SOM) that uses a geographic like landscape  
>>>>>>> metaphor for
>>>>>>> visualisation***, and recently hooked up a text front end for
>>>>>>> extracting
>>>>>>> word distance metrics from bodies of text ? I've been testing  
>>>>>>> it on
>>>>>>> works of
>>>>>>> literature from Project Gutenberg up to now, but have wanted  
>>>>>>> to try
>>>>>>> it on
>>>>>>> bulk mail feeds for a while.
>>>>>>>
>>>>>>> *** Code is all Python/PIL but too CPU intensive for an XO,  
>>>>>>> though
>>>>>>> it might
>>>>>>> make nice visual index/content pages for wiki content and  
>>>>>>> such, with
>>>>>>> URL
>>>>>>> links...
>>>>>>>
>>>>>>> The SOM acts as a kind of spacial summariser visualisation of  
>>>>>>> the
>>>>>>> content,
>>>>>>> where height indicates strong connections between terms,  
>>>>>>> proximity
>>>>>>> represents term association, and label size is a rough guide  
>>>>>>> to basic
>>>>>>> frequency of the term. Now there are many "correct" maps for the
>>>>>>> same set of
>>>>>>> data, each generation will usually settle into a slightly  
>>>>>>> different
>>>>>>> set of
>>>>>>> local minima, but the associations are no less valid for each.
>>>>>>>
>>>>>>> It's currently picking the top ~200 terms by frequency, after  
>>>>>>> removing
>>>>>>> linguistic junk words. Here's the map that generated for the
>>>>>>> Its.an.education.project May archives, as of yesterday. Note  
>>>>>>> that
>>>>>>> the map is
>>>>>>> continuous (wraps around North/South and East/West, surface of  
>>>>>>> a torus
>>>>>>> actually).
>>>>>>>
>>>>>>> Probably just a curiosity, but might be more useful on your disk
>>>>>>> than mine.
>>>>>>>
>>>>>>> --Gary
>